Search papers, labs, and topics across Lattice.
Affiliation:
4
7
8
18
Transforming zero-reward training instances into valuable learning opportunities, HCGRec cuts down ineffective samples from over 70% to under 20%.
MARA achieves 63.46% task completion in resource-constrained environments, outperforming existing methods by over 8 percentage points.
LLMs' final layers might be holding your recommendation system back: representations from middle layers actually perform *better*, and a modular compression approach can unlock significant gains.
Current LLM evaluation benchmarks often conflate chatbots and true AI agents, leading to misaligned research efforts, but this survey provides a framework for targeted evaluation based on environmental complexity and agent capabilities.
